logo
today local_bar

Jacob Andreas

Associate Professor, Massachusetts Institute of Technology

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

1 paper
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Learning Linear Attention in Polynomial Time
#3515 · Morris Yau, Ekin Akyürek, Jiayuan Mao, Joshua B. Tenenbaum, Stefanie Jegelka, Jacob Andreas

We develop algorithms that are guaranteed to PAC learn transformers.

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
#1002 · Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet, Jacob Andreas, Agata Lapedriza, Antonio Torralba, Tamar Rott Shaham

Automated agent with a self-reflection mechanism that detects unintended visual attribute dependencies in vision models

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
LoRA vs Full Fine-tuning: An Illusion of Equivalence
#5500 · Reece S Shuttleworth, Jacob Andreas, Antonio Torralba, Pratyusha Sharma